The workshop will be held in 316C.

Program

13:30	Opening Remarks
13:35	Keynote 1: ANGELA YAO, NATIONAL UNIVERSITY OF SINGAPORE, SG - Visual AI Assistance: From Seeing Towards Helping
14:05	ORAL SESSION 1
14:35	Abstracts
14:45	POSTER SESSION AND COFFEE BREAK
16:00	Keynote 2: DAEKYUM KIM, KOREA UNIVERSITY, KR - Vision-based Intelligence for Assistive Wearable Robots
16:30	ORAL SESSION 2
17:00	Doctoral Consortium
17:10	Closing Remarks

Oral Session 1* (8 minutes presentation + 2 minutes Q&A)

• Antonio Luigi Stefani (Università di Trento)*; Sara Baldoni (Università di Padova); Niccolò Bisagno (Università di Trento); Federica Battisti (Università di Padova); Nicola Conci (Università di Trento); Francesco De Natale (Università di Trento) . Understanding touch through latent spaces: can images and haptic maps reflect human perception?
• Riccardo Catalini (University of Modena and Reggio Emilia); Giacomo Salici (University of Modena and Reggio Emilia)*; Federico Biagi (University of Modena and Reggio Emilia); Guido Borghi (University of Modena and Reggio Emilia); Luigi Biagiotti (University of Modena and Reggio Emilia); Roberto Vezzani (University of Modena and Reggio Emilia) . LLMs as NAO Robot 3D Motion Planners
• Jiazhao Liang (New York University)*; Yi Fang (New York University) . CrossCompanion: An Empathetic Real-Time Assistant Supporting Street Crossing for Low-Vision Users

Abstracts* (8 minutes presentation + 2 minutes Q&A)

• Lorenzo Mur-Labadia (Universidad de Zaragoza); Maria Santos-Villafranca (Universidad de Zaragoza)*; Jesus Bermudez-Cameo (Universidad de Zaragoza); Alejandro Perez-Yus (Universidad de Zaragoza); Ruben MArtinez-Cantin (Universidad de Zaragoza); Jose J. Guerrero (Universidad de Zaragoza) . O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views

Poster Session

Poster size: see here: https://iccv.thecvf.com/Conferences/2025/PosterPrinting

The poster session will be held in Exhall II. Authors should use the poster boards corresponding to the assigned poster numbers below.

#	Paper
135	Jiazhao Liang (New York University); Yi Fang (New York University). CrossCompanion: An Empathetic Real-Time Assistant Supporting Street Crossing for Low-Vision Users
136	JINSE KWON (Electronics and Telecommunications Research Institute); JEMIN LEE (Electronics and Telecommunications Research Institute); YONGIN KWON (Electronics and Telecommunications Research Institute). Design Practices and Lessons from Deploying On-device Vision-Language Interaction in Robotic Guide Dogs
137	Jiajie Lu (Politecnico di Milano); Viviana Desantis (Politecnico di Milano); Marco Brando Mario Paracchini (Politecnico di Milano); Marco Marcon (Politecnico di Milano). Enhancing Low-Light Vision: An Efficient Infrared-Visible Fusion Approach
138	Chanhyuk Jung (Keimyung University); Sangwon Kim (ETRI); Kwangju Kim (ETRI); Dasom Ahn (Keimyung University); Joonki Baek (Keimyung University); Sungkeun Yoo (Keimyung University); Byoung Chul Ko (Keimyung University). Flow-Guided Policies: Overcoming Diffusion Limitations for Robust Robot Imitation Learning
139	Riccardo Catalini (University of Modena and Reggio Emilia); Giacomo Salici (University of Modena and Reggio Emilia); Federico Biagi (University of Modena and Reggio Emilia); Guido Borghi (University of Modena and Reggio Emilia); Luigi Biagiotti (University of Modena and Reggio Emilia); Roberto Vezzani (University of Modena and Reggio Emilia). LLMs as NAO Robot 3D Motion Planners
140	Jun Yu (Lehigh University); Yitian Yang (Lehigh University); Vinod Namboodiri (Lehigh University). NaVIP: A Low-Cost, Infrastructure-free Indoor Navigation Solution for Visually Impaired Persons
141	Filippos Bellos (University of Michigan); Yayuan Li (University of Michigan); Cary Shu (University of Michigan); Ruey Day (University of Michigan); Jeffrey Siskind (Purdue University); Jason Corso (University of Michigan). Towards Effective Human-in-the-Loop Assistive AI Agents
142	Giuseppe De Simone (University of Salerno); Loris Roveda (SUPSI); Alessia Saggese (University of Salerno); Mario Vento (University of Salerno). Towards Proactive Social Robots: Distilling Visual Knowledge from Large Vision-Language Models
143	Choonghan Lee (Electronics and Telecommunications Research Institute); Leah Harris (University of Nevada, Las Vegas); Sehyeon Oh (University of Science and Technology); JooHyoung Cha (University of Science and Technology); Jemin Lee (Electronics and Telecommunications Research Institute); Yongin Kwon (Electronics and Telecommunications Research Institute); Andrew Jang-ho Bae (University of Nevada, Las Vegas). TriPlanNet: Triangle Path Planning Network for A Variable Truss Robot with Deep Learning
144	Antonio Luigi Stefani (Università di Trento); Sara Baldoni (Università di Padova); Niccolò Bisagno (Università di Trento); Federica Battisti (Università di Padova); Nicola Conci (Università di Trento); Francesco De Natale (Università di Trento). Understanding touch through latent spaces: can images and haptic maps reflect human perception?
145	Ryan Hansen (New York University); Hardik Setia (New York University); Giles Hamilton-Fletcher (New York University Langone Health); Aryan Jain (New York University); Zirui Liu (New York University); Mariam Zoair (New York University); Reem Aboutaleb (New York University); Qing Wen (New York University); Yu Li (Columbia University); John-Ross Rizzo (New York University Langone Health). Visual Language Model-based Food Safety Support for Persons with Blindness and Low Vision
146	(Abstract) Lorenzo Mur-Labadia (Universidad de Zaragoza); Maria Santos-Villafranca (Universidad de Zaragoza); Jesus Bermudez-Cameo (Universidad de Zaragoza); Alejandro Perez-Yus (Universidad de Zaragoza); Ruben Martinez-Cantin (Universidad de Zaragoza); Jose J. Guerrero (Universidad de Zaragoza). O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views
147	(Doctoral Consortium) Simone Alberto Peirone (Politecnico di Torino); Francesca Pistilli (Politecnico di Torino); Giuseppe Averta (Politecnico di Torino). Exploiting hierarchy and compositionality to understand human behavior

Oral Session 2* (8 minutes presentation + 2 minutes Q&A)

• Filippos Bellos (University of Michigan); Yayuan Li (University of Michigan)*; Cary Shu (University of Michigan); Ruey Day (University of Michigan); Jeffrey Siskind (Purdue University); Jason Corso (University of Michigan) . Towards Effective Human-in-the-Loop Assistive AI Agents
• Jun Yu (Lehigh University)*; Yitian Yang (Lehigh University); Vinod Namboodiri (Lehigh University) . NaVIP: A Low-Cost, Infrastructure-free Indoor Navigation Solution for Visually Impaired Persons
• Giuseppe De Simone (University of Salerno)*; Loris Roveda (SUPSI); Alessia Saggese (University of Salerno); Mario Vento (University of Salerno) . Towards Proactive Social Robots: Distilling Visual Knowledge from Large Vision-Language Models

Doctoral Consortium* (10 minutes presentation including questions)

• Simone Alberto Peirone (Politecnico di Torino)*; Francesca Pistilli (Politecnico di Torino); Giuseppe Averta (Politecnico di Torino) . Exploiting hierarchy and compositionality to understand human behavior

All papers that will be presented as oral/abstract/doctoral will also be presented as poster